• Publications
  • Influence
iCoseg: Interactive co-segmentation with intelligent scribble guidance
This paper presents an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous approaches focus on unsupervised co-segmentation, we useExpand
  • 432
  • 46
Fusion4D: real-time performance capture of challenging scenes
We contribute a new pipeline for live multi-view performance capture, generating temporally coherent high-quality reconstructions in real-time. Our algorithm supports both incremental reconstruction,Expand
  • 219
  • 24
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-freeExpand
  • 66
  • 15
Holoportation: Virtual 3D Teleportation in Real-time
We present an end-to-end system for augmented and virtual reality telepresence, called Holoportation. Our system demonstrates high-quality, real-time 3D reconstructions of an entire space, includingExpand
  • 220
  • 13
Multiple View Object Cosegmentation Using Appearance and Stereo Cues
We present an automatic approach to segment an object in calibrated images acquired from multiple viewpoints. Our system starts with a new piecewise planar layer-based stereo algorithm that estimatesExpand
  • 56
  • 13
Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance
We present an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous works in co-segmentation have focussed on unsupervised co-segmentation,Expand
  • 104
  • 11
Articulated distance fields for ultra-fast tracking of hands interacting
The state of the art in articulated hand tracking has been greatly advanced by hybrid methods that fit a generative hand model to depth data, leveraging both temporally and discriminatively predictedExpand
  • 35
  • 5
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems
In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems. Due to the lack of ground truth, our method is fully self-supervised, yet it produces preciseExpand
  • 32
  • 5
Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
Scene understanding includes many related subtasks, such as scene categorization, depth estimation, object detection, etc. Each of these subtasks is often notoriously hard, and state-of-the-artExpand
  • 101
  • 4
Motion2fusion: real-time volumetric performance capture
We present Motion2Fusion, a state-of-the-art 360 performance capture system that enables *real-time* reconstruction of arbitrary non-rigid scenes. We provide three major contributions over priorExpand
  • 67
  • 4